INDEX

Explanations

fragments related to academic citations and references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TestingModule

-0.54

ttemberg

-0.47

 NUKAT

-0.44

 Réponses

-0.44

quera

-0.41

 quilting

-0.39

δε

-0.39

 विश्वसनीयता

-0.38

vábbi

-0.38

POSITIVE LOGITS

下载附件

0.93

MENAFN

0.92

imageshack

0.76

]--;

0.76

 purpoſe

0.72

 transfieras

0.71

ագրություններ

0.70

 considérons

0.70

Przypisy

0.69

 themſelves

0.67

Activations Density 5.107%

fragments related to academic citations and references

No Comments

No Known Activations